Skip to main content
GET
/
llms
List LLMs
curl --request GET \
  --url https://api.dialnexa.com/v1/llms \
  --header 'Authorization: Bearer <token>'
{
  "data": [
    {
      "id": "llm_gpt4o",
      "name": "GPT-4o",
      "provider": "openai",
      "description": "Best overall performance for complex conversations.",
      "is_default": false
    }
  ]
}
Returns every large language model available to power DialNexa agents. Each entry includes the model’s stable id, display name, upstream provider (such as OpenAI, Google, Groq, or DeepSeek), the supported context window, and the conversational features the model exposes (function calling, JSON mode). Use the id field as the value for llm.id when creating or updating an agent. The catalogue evolves continually as providers ship new models, so always call this endpoint at deploy time rather than hard-coding the list.

​
When to use this

  • Agent build UIs: populate the LLM selector when creating or editing an agent.
  • Provider diversification: choose models from multiple providers so an upstream incident with one provider does not take down every agent.
  • Cost optimization: switch high-volume agents to smaller models when conversational quality stays acceptable.
  • Capability filtering: find models that support function calling for agents that need tool use, or models with large context windows for long conversations.

​
How to choose an LLM

The right LLM depends on the use case:
  • Simple, high-volume agents (appointment reminders, opt-in confirmations): smaller and cheaper models like GPT-4o Mini or DeepSeek V3 typically suffice.
  • Conversational quality matters (consultative sales, sensitive support): larger models like GPT-4o or GPT-4.1 typically perform better on tone, recovery, and multi-turn reasoning.
  • Latency-sensitive flows: Groq-hosted models offer extremely low first-token latency at the cost of some conversational quality.
  • Multilingual or India-first: confirm the model handles your target language well by testing with the LLM Playground before publishing.
See LLMs and conversation behavior for deeper guidance.

​
Errors

  • 401 Unauthorized is returned when the API key is missing or revoked.

​
Request

curl "https://api.dialnexa.com/v1/llms" \
  -H "Authorization: Bearer YOUR_API_KEY"

​
Response

{
  "data": [
    { "id": "llm_gpt4o_mini",  "name": "GPT-4o Mini",    "provider": "openai"   },
    { "id": "llm_gpt4o",       "name": "GPT-4o",         "provider": "openai"   },
    { "id": "llm_gpt41",       "name": "GPT-4.1",        "provider": "openai"   },
    { "id": "llm_groq_llama4", "name": "Llama 4 Scout",  "provider": "groq"     },
    { "id": "llm_deepseek_v3", "name": "DeepSeek V3",    "provider": "deepseek" },
    { "id": "llm_gemini",      "name": "Gemini",         "provider": "google"   }
  ]
}
The model list is dynamic. New models are added without a breaking API change. Always call GET /v1/llms to retrieve the current list rather than hard-coding model IDs.

Authorizations

​
Authorization
string
header
required

Pass your API key as a Bearer token in the Authorization header.

Response

200 - application/json

Success.

​
data
object[]